{
 "id": "acul3/KoPI-CC",
 "owner": "acul3",
 "name": "KoPI-CC",
 "downloads": 5178,
 "likes": 1,
 "last_modified": "2023-03-03T08:14:38.000Z",
 "stated_licence": "cc",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@ARTICLE{2022arXiv220106642A,\n\nauthor = {{Abadji}, Julien and {Ortiz Suarez}, Pedro and {Romary}, Laurent and {Sagot}, Beno{\\^\\i}t},\n\ntitle = \"{Towards a Cleaner Document-Oriented Multilingual Crawled Corpus}\",\n\njournal = {arXiv e-prints},\n\nkeywords = {Computer Science - Computation and Language},\n\nyear = 2022,\n\nmonth = jan,\n\neid = {arXiv:2201.06642},\n\npages = {arXiv:2201.06642},\n\narchivePrefix = {arXiv},\n\neprint = {2201.06642},\n\nprimaryClass = {cs.CL},\n\nadsurl = {https://ui.adsabs.harvard.edu/abs/2022arXiv220106642A},\n\nadsnote = {Provided by the SAO/NASA Astrophysics Data System}\n\n}\n\n@inproceedings{AbadjiOrtizSuarezRomaryetal.2021,\n\nauthor = {Julien Abadji and Pedro Javier Ortiz Su{\\'a}rez and Laurent Romary and Beno{\\^i}t Sagot},\n\ntitle = {Ungoliant: An optimized pipeline for the generation of a very large-scale multilingual web corpus},\n\nseries = {Proceedings of the Workshop on Challenges in the Management of Large Corpora (CMLC-9) 2021. Limerick, 12 July 2021 (Online-Event)},\n\neditor = {Harald L{\\\"u}ngen and Marc Kupietz and Piotr Bański and Adrien Barbaresi and Simon Clematide and Ines Pisetta},\n\npublisher = {Leibniz-Institut f{\\\"u}r Deutsche Sprache},\n\naddress = {Mannheim},\n\ndoi = {10.14618/ids-pub-10468},\n\nurl = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-104688},\n\npages = {1 -- 9},\n\nyear = {2021},\n\nabstract = {Since the introduction of large language models in Natural Language Processing, large raw corpora have played a crucial role in Computational Linguistics. Ho",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "39fada6cd52f101ea2731456009bc6469b4d5a78",
 "stated_evidence": "https://huggingface.co/datasets/acul3/KoPI-CC/blob/39fada6cd52f101ea2731456009bc6469b4d5a78/README.md",
 "file_evidence": "https://huggingface.co/datasets/acul3/KoPI-CC/tree/39fada6cd52f101ea2731456009bc6469b4d5a78",
 "card_nc": false
}